AI mention mix (type/tone/qualifier)

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare this a safe, idempotent read, so the bar is lower. The description still adds real behavioral context beyond structured fields: counts are raw per-pass rows, cited links are excluded, and results are not directly the share-of-voice inputs (which average passes and weight links). It does not describe return shape, but the caveats about counting semantics are genuinely useful.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core operation and exclusions, then escalation to alternatives. Mostly earns its sentences, though 'Use to understand mention composition' is slightly redundant with the opening clause and the share-of-voice digression is dense.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and modest param coverage, the description does the heavy lifting: it defines exclusions, counting semantics, retention constraints, and routes to two sibling tools. An agent has enough to call it correctly, though the identity parameters remain undocumented.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 33% across 6 params. The description partially compensates by stating dates must fall within the data retention window (a real constraint on dateFrom/dateTo) and by noting competitor/unrelated-brand exclusion, but organizationId, projectId, engines and countries carry no added meaning in the description beyond the schema's own notes and the get_available_filters pointer.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource (brand's own AI text-mention counts), the grouping dimensions (type, tone, qualifier), the date window scope, and the exclusion rules for competitors and unrelated brands. An agent can distinguish this from get_share_of_voice_formula or get_sentiment_breakdown without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Names alternatives explicitly and the conditions selecting them: get_sentiment_breakdown for the positive/neutral/negative split, get_mention_samples for the actual mention texts. It also frames the intent of the tool ('understand mention composition') and gives example questions, so when/when-not is fully resolved.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.